Passer à la navigation principale Passer à la recherche Passer au contenu principal

Top Two Algorithms Revisited

  • Marc Jourdan
  • , Rémy Degenne
  • , Dorian Baudry
  • , Rianne de Heide
  • , Emilie Kaufmann

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collectionContribution à une conférenceRevue par des pairs

Résumé

Top Two algorithms arose as an adaptation of Thompson sampling to best arm identification in multi-armed bandit models [38], for parametric families of arms. They select the next arm to sample from by randomizing among two candidate arms, a leader and a challenger. Despite their good empirical performance, theoretical guarantees for fixed-confidence best arm identification have only been obtained when the arms are Gaussian with known variances. In this paper, we provide a general analysis of Top Two methods, which identifies desirable properties of the leader, the challenger, and the (possibly non-parametric) distributions of the arms. As a result, we obtain theoretically supported Top Two algorithms for best arm identification with bounded distributions. Our proof method demonstrates in particular that the sampling step used to select the leader inherited from Thompson sampling can be replaced by other choices, like selecting the empirical best arm.

langue originaleAnglais
titreAdvances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022
rédacteurs en chefS. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, A. Oh
EditeurNeural information processing systems foundation
ISBN (Electronique)9781713871088
étatPublié - 1 janv. 2022
Modification externeOui
Evénement36th Conference on Neural Information Processing Systems, NeurIPS 2022 - New Orleans, États-Unis
Durée: 28 nov. 20229 déc. 2022

Série de publications

NomAdvances in Neural Information Processing Systems
Volume35
ISSN (imprimé)1049-5258

Une conférence

Une conférence36th Conference on Neural Information Processing Systems, NeurIPS 2022
Pays/TerritoireÉtats-Unis
La villeNew Orleans
période28/11/229/12/22

Empreinte digitale

Examiner les sujets de recherche de « Top Two Algorithms Revisited ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation